© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 88355
    Prev
    Next
    INDEX
    Explanations

    words related to restrictions and conditional statements in policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uffy
    -0.07
    ConverterFactory
    -0.07
    ground
    -0.06
     bounded
    -0.06
    isy
    -0.06
     recurs
    -0.05
     synthes
    -0.05
     ä½IJ
    -0.05
    irim
    -0.05
    osi
    -0.05
    POSITIVE LOGITS
    ansi
    0.07
    interop
    0.07
    OTS
    0.07
    ANJI
    0.07
    lagen
    0.07
    ÑĨÑİ
    0.07
    lingen
    0.07
    eshire
    0.06
     '".
    0.06
    alars
    0.06
    Activations Density 0.001%

    No Known Activations